Stability of annealing schemes and related processes

被引:5
作者
Borkar, VS [1 ]
机构
[1] Tata Inst Fundamental Res, Sch Technol & Comp Sci, Bombay 400005, Maharashtra, India
关键词
stochastic algorithms; stochastic stability; annealing processes; scaling limits;
D O I
10.1016/S0167-6911(00)00073-6
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
An approach for establishing stability of annealing schemes and related processes is described. This extends the approach developed in Borkar and Meyn (SIAM J. Control Optim. 38 (2000) 447) for stochastic approximation algorithms. The proof uses a possibly degenerate stochastic differential equation obtained as a scaling limit of the interpolated algorithm. (C) 2000 Elsevier Science B.V. All rights reserved.
引用
收藏
页码:325 / 331
页数:7
相关论文
共 12 条
[1]   Weak convergence of recursions [J].
Basak, GK ;
Hu, IC ;
Wei, CZ .
STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 1997, 68 (01) :65-82
[2]  
Benveniste A, 1990, Adaptive algorithms and stochastic approximations
[3]  
Billingsley P, 1968, CONVERGE PROBAB MEAS
[4]   A strong approximation theorem for stochastic recursive algorithms [J].
Borkar, VS ;
Mitter, SK .
JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 1999, 100 (03) :499-513
[5]   The ODE method for convergence of stochastic approximation and reinforcement learning [J].
Borkar, VS ;
Meyn, SP .
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 2000, 38 (02) :447-469
[6]  
ETHIER S., 1986, MARKOV PROCESSES CHA, DOI 10.1002/9780470316658
[7]   Annealing of iterative stochastic schemes [J].
Fang, HT ;
Gong, GL ;
Qian, MP .
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 1997, 35 (06) :1886-1907
[8]   RECURSIVE STOCHASTIC ALGORITHMS FOR GLOBAL OPTIMIZATION IN RD [J].
GELFAND, SB ;
MITTER, SK .
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 1991, 29 (05) :999-1018
[9]  
KUMAR P. R., 2015, Stochastic Systems: Estimation, Identification, and Adaptive Control
[10]  
Liptser R. S, 1977, STAT RANDOM PROCESSE, pI